[squid-users] AUFS vs. DISKS

[Amos Jeffries]

On 16/07/2015 1:51 a.m., Stakres wrote:
> Hi Fred,
> tests from my side:
> DISKD with TCP_HIT objects: 564KB/s with wget, the same url you have tested.
> AUFS with TCP_HITS objects: 47.8M/s, same wget, same squid, same url, same
> all.
> 
> Wget with AUFS:
> Length: 10095849 (9.6M) [application/x-msdos-program]
> Saving to: `youtube_downloader_hd_setup-2.9.9.23.exe'
> 100%[======================================>] 10,095,849  47.9M/s   in 0.2s
> 2015-07-15 15:48:29 (47.9 MB/s) - `youtube_downloader_hd_setup-2.9.9.23.exe'
> saved
> 
> All,
> We have switched some ISPs from DISKD to AUFS this morning, the "queue
> congestion" appears at the begining then disappears from the cache.log. For
> how long, nobody knows...


Doh. Sorry its been so long I had forgotten one detail ...

Squid AUFS starts with a relatively short I/O queue length (8 entries)
and auto-grows it as needed by doubling the limit and displaying the
congestion message. On any busy proxy this can be seen for a while after
startup, then possibly during the first traffic peak after that. It is
not a problem unless it keeps growing indefinitely or appears suddenly
without a matching traffic spike (possible sign of disk failure).

I'm applying a patch to raise the baseline queue length from 8 to 8K,
and reporting in each message what the limit was changed to. That should
get rid of a dozen entries in your logs, and help show whats going on in
the remainder.

Amos